This repository contains the code for the Computer Vision Toolbox with OpenCV and Streamlit.
The toolbox is a playground of computer vision algorithms implemented in Python using OpenCV and Streamlit.
The toolbox is organized into several sections, each focusing on a specific area of computer vision:
- Cropping: Extract regions of interest from images.
- Change Color Space: Convert images between different color spaces (e.g., RGB, HSV, Grayscale).
- Morphological Operations: Perform operations like erosion, dilation, and opening/closing.
- Edge Detection: Detect edges using algorithms like Canny or Sobel.
- Contour Detection: Identify and analyze object boundaries.
- Histogram: Visualize pixel intensity distributions.
- Image Transformation: Apply transformations such as rotation, scaling, and affine transformations.
- Feature Matching: Match keypoints between two images.
- Matching + Homography: Compute homographies for image alignment.
- Harris Corner Detection: Detect corners in images.
- Good Features to Track: Identify stable features for tracking.
- SIFT: Scale-Invariant Feature Transform for robust feature detection.
- SURF: Speeded-Up Robust Features for fast detection.
- FAST: Fast corner detection algorithm.
- ORB: Oriented FAST and Rotated BRIEF for efficient feature extraction.
- Non-photorealistic Rendering: Apply artistic effects to images.
- Face Detection: Detect faces in images using pre-trained models.
- Landmark Detection: Identify facial landmarks for applications like pose estimation.
- Face Recognition: Recognize individuals using facial features.
- Facial Filters: Apply fun filters to live video streams.
- Document Scanner: Automatically detect and scan documents.
- OCR: Extract text from images using Optical Character Recognition.
To install the required dependencies, run the following command:
pip install -r requirements.txtstreamlit run cv_toolbox.py